训练属于自己的dataset

训练属于自己的dataset

由于作者大部分工作在ubuntu完成，所以主要以ubuntu系统为主。

1.配置conda环境：

去官方网装好anaconda.

打开终端，创建新的conda环境并进入：

conda create --name labelme python=3.6
conda activate labelme

2.安装labelme:

# conda install -c conda-forge pyside2
# conda install pyqt
# pip install pyqt5  # pyqt5 can be installed via pip on python3
pip install labelme
# or you can install everything by conda command
# conda install labelme -c conda-forge

3.使用labelme

用法像ps的套索工具并打上标签

4.批量处理json_to_dataset

此工作在window中进行

同样，先装好conda.并装好pycharm

新建一个py文件，命名为json_to_dataset,并把conda环境加入其中。

import argparse
import json
import os
import os.path as osp
import warnings

import PIL.Image
import yaml

from labelme import utils
import base64


def main():
    warnings.warn("This script is aimed to demonstrate how to convert then"
                  "JSON file to a single image dataset, and not to handlen"
                  "multiple JSON files to generate a real-use dataset.")
    parser = argparse.ArgumentParser()
    parser.add_argument('json_file')
    parser.add_argument('-o', '--out', default=None)
    args = parser.parse_args()

    json_file = args.json_file
    if args.out is None:
        out_dir = osp.basename(json_file).replace('.', '_')
        out_dir = osp.join(osp.dirname(json_file), out_dir)
    else:
        out_dir = args.out
    if not osp.exists(out_dir):
        os.mkdir(out_dir)

    count = os.listdir(json_file)
    for i in range(0, len(count)):
        path = os.path.join(json_file, count[i])
        if os.path.isfile(path):
            data = json.load(open(path))

            if data['imageData']:
                imageData = data['imageData']
            else:
                imagePath = os.path.join(os.path.dirname(path), data['imagePath'])
                with open(imagePath, 'rb') as f:
                    imageData = f.read()
                    imageData = base64.b64encode(imageData).decode('utf-8')
            img = utils.img_b64_to_arr(imageData)
            label_name_to_value = {'_background_': 0}
            for shape in data['shapes']:
                label_name = shape['label']
                if label_name in label_name_to_value:
                    label_value = label_name_to_value[label_name]
                else:
                    label_value = len(label_name_to_value)
                    label_name_to_value[label_name] = label_value

            # label_values must be dense
            label_values, label_names = [], []
            for ln, lv in sorted(label_name_to_value.items(), key=lambda x: x[1]):
                label_values.append(lv)
                label_names.append(ln)
            assert label_values == list(range(len(label_values)))

            lbl = utils.shapes_to_label(img.shape, data['shapes'], label_name_to_value)

            captions = ['{}: {}'.format(lv, ln)
                        for ln, lv in label_name_to_value.items()]
            lbl_viz = utils.draw_label(lbl, img, captions)

            out_dir = osp.basename(count[i]).replace('.', '_')
            out_dir = osp.join(osp.dirname(count[i]), out_dir)
            if not osp.exists(out_dir):
                os.mkdir(out_dir)

            PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png'))
            # PIL.Image.fromarray(lbl).save(osp.join(out_dir, 'label.png'))
            utils.lblsave(osp.join(out_dir, 'label.png'), lbl)
            PIL.Image.fromarray(lbl_viz).save(osp.join(out_dir, 'label_viz.png'))

            with open(osp.join(out_dir, 'label_names.txt'), 'w') as f:
                for lbl_name in label_names:
                    f.write(lbl_name + 'n')

            warnings.warn('info.yaml is being replaced by label_names.txt')
            info = dict(label_names=label_names)
            with open(osp.join(out_dir, 'info.yaml'), 'w') as f:
                yaml.safe_dump(info, f, default_flow_style=False)

            print('Saved to: %s' % out_dir)


if __name__ == '__main__':
    main()

点击右上角json_to_dataset一栏，edit configuration.

 

 

在parameters一栏填入labelme处理好的json的文件夹.

 

此时按运行就会在json_to_dataset.py路径下生成dataset.

未完，待续